Abstract: The invention provides a cellular telephone or other communications device with intelligence to manage speakerphone operation to more nearly approximate normal conversation, even when using a one-way only transmission mode. The microphone path and speaker path may be continuously monitored using dual voice activity detectors to assess the energy and other characteristics of each channel, and switch between one or the other depending on dynamic criteria. In noisy environments, a hangtime may be applied before permitting switching to avoid premature dropouts. Other criteria used to trigger the seizure of the channel may be adjusted, such as to eliminate a lower threshold below which the speaker path switches out automatically.

Abstract: The invention equips a cellular telephone or other communications device with improved voice recognition and command capability. A cellular handset may be equipped with a digital signal processing or other hardware to enhance speech detection and command decoding, but still be relatively constrained in terms of the amount of electronic memory or other storage available on the device, or the processing power or battery life offered by the device. In embodiments, the cellular handset or other device may perform a first-stage decoding of a voice or other command, for instance to perform a voice browsing function over the Internet or a directory. The handset may perform a look-up of the detected command or service against a local memory cache of stored commands, services and models and if a match is found, proceed directly to performing the desired service.

Abstract: The invention provides a method and system for dynamically estimating background noise comprising. The system includes a portable communication device, a vocoder, and a voice activated detector. Based on information received by the portable communication device, the vocoder determines parameters related to incoming information including a voicing mode indicative of the periodicity of incoming information. The voice activated detector then compares the voicing mode to a threshold to determine whether a background noise estimate should be updated.

Abstract: A mobile communication device (100) determines a background noise level at a microphone (104). If, after determining the noise floor, the input signal exceeds a threshold, the mobile communication device transmits the input signal. The threshold is established such that if it is exceeded, it is likely that voice energy is being received at the microphone, and the threshold, in a first embodiment, is increased as the background noise level increases. In a second embodiment the threshold is determined as the difference between the input signal and the background noise level. As background noise increases, the threshold actually decreases.

Abstract: A speakerphone arbitration method is used to eliminate the effects of echo in imperfect telephone circuits. The method assumes that speech energy received at the speaker phone is an echo, unless the speech energy has characteristics that indicate it is not echo, such as the duration of the speech energy, and the time at which the speech energy is received relative to the time when the user of the speakerphone finishes speaking, or pauses while speaking. The method also may allow arbitration if the speech energy is more energetic than a typical echo, regardless of the duration or time when it is received.

Abstract: A speakerphone arbitration method is used to eliminate the effects of echo in imperfect telephone circuits. The method assumes that speech energy received at the speaker phone is an echo, unless the speech energy has characteristics that indicate it is not echo, such as the duration of the speech energy, and the time at which the speech energy is received relative to the time when the user of the speakerphone finishes speaking, or pauses while speaking. The method also may allow arbitration if the speech energy is more energetic than a typical echo, regardless of the duration or time when it is received.